HTCondor / ARC CE Workshop

Europe/Zurich
ALBA Synchrotron

ALBA Synchrotron

Carrer de la Llum 2-26 08290 Cerdanyola del Vallès, Barcelona, Spain Tel: +34 93 592 43 00 Coordinates: +41°29'12.38", +2°6'35.74" (41.486773, 2.109929)
Brian Paul Bockelman (University of Nebraska (US)), Helge Meinhard (CERN), Jon Kerr Nilsen (University of Oslo (NO)), Jose Flix Molina (Centro de Investigaciones Energ. Medioambientales y Tecn. - (ES), Marc Rodriguez (ALBA), Mario Diaz-Laguardia (Alba Synchrotron), Todd Tannenbaum (Univ of Wisconsin-Madison, Wisconsin, USA)
Description

The workshop, second one after the successful workshop at CERN in December 2014, is an opportunity for novice and experienced users of HTCondor to learn, get help and have exchanges between them and with the HTCondor and ARC developers and experts. It is primarily addressed at users from EMEA. The workshop will consist of presentations, tutorials and "office hours" for consultancy. The HTCondor CE (Compute Element) as well as the ARC CE will be covered as well. ALBA Synchrotron Light facility located in Cerdanyola del Vallès (Barcelona) act as the event host, with the additional help of Port d'Informació Científica (PIC) for event preparation/coordination. There is a fee of 80€ (VAT included) which covers the lunches and all coffee breaks along the event.

 

Participants
  • Almudena Montiel González
  • Andre Sailer
  • Andrew Lahiff
  • Antonio Delgado Peris
  • Antonio Perez-Calero Yzquierdo
  • Antonio Puertas Gallardo
  • Aresh Vedaee
  • Ben Jones
  • Brian Paul Bockelman
  • Carlos Acosta Silva
  • Catalin Condurache
  • Christelle Eloto
  • Christian Søttrup
  • Christoph Beyer
  • Dimitri Nilsen
  • Dino Conciatore
  • Emilis Antanas Rupeika
  • Feras Awaysheh
  • Francesco Prelz
  • Gianni Mario Ricciardi
  • Guillaume Philippon
  • Helge Meinhard
  • Henning Fehrmann
  • Houssam MOUDJEB
  • Iain Bradford Steers
  • ILYEON YEO
  • Ingrid Kulkova
  • Jaime Frey
  • Jan Erik Sundermann
  • Jan Svec
  • Jaume Timoneda Salat
  • Jean-Michel Barbet
  • Joao Pina
  • John Knoeller
  • Jon Kerr Nilsen
  • Jordi Casals
  • Jordi Peralta
  • Jordi Pons i Prats
  • Jose Flix Molina
  • Justas Balcas
  • Lukasz Kreczko
  • Marc Rodriguez
  • Mario Diaz-Laguardia
  • Martin Skou Andersen
  • Martí Coma Company
  • Michel Jouvin
  • Miloslav Straka
  • Miron Livny
  • Paul Hopkins
  • Pavlo Svirin
  • Pier Valerio Tognoli
  • Ramon Escriba
  • RAMPARISON Adrien
  • Renaud Vernet
  • Ricard Cruz Josa
  • Romain Rougny
  • Sangwook Bae
  • Shao-Ting Cheng
  • Stefano Dal Pra
  • Stephane GERARD
  • Stephen Jones
  • Thomas Hartmann
  • Todd Tannenbaum
  • Zach Miller
    • 9:00 AM 10:10 AM
      HTCondor presentations and tutorials
      • 9:00 AM
        HTCondor Policies: Job and Machines 50m
        Speaker: Todd Tannenbaum (Univ of Wisconsin-Madison, Wisconsin, USA)
      • 9:50 AM
        Configuring HTCondor for ATLAS Multicore 20m
        Configuring ARC/Condor for ATLAS Multicore This talk will cover the specific measures used at the Liverpool grid site to provide multicore job slots for ATLAS using an ARC CE in front of a CONDOR batch system.
        Speaker: Mr Stephen Jones (Liverpool)
    • 10:10 AM 10:40 AM
      Coffee Break 30m
    • 10:40 AM 12:00 PM
      HTCondor presentations and tutorials
    • 12:00 PM 1:00 PM
      Lunch 1h
    • 1:30 PM 3:30 PM
      HTCondor presentations and tutorials
    • 3:30 PM 4:00 PM
      Coffee Break 30m
    • 4:00 PM 6:20 PM
      HTCondor presentations and tutorials
      • 4:00 PM
        Best Practices - Monitoring 30m
        Speaker: Todd Tannenbaum (Univ of Wisconsin-Madison, Wisconsin, USA)
      • 4:30 PM
        Effective HTCondor-based monitoring system 30m
        The CMS experiment at LHC relies on HTCondor and glideinWMS as its primary batch and pilot-based grid provisioning systems. Given the scale of the global queue in CMS, operators found it increasingly difficult to monitor the pool to find issues and fix them. Operators had to rely on several different webpages, with several different levels of information and sifting tirelessly through logs in order to monitor the pool completely. Therefore, coming up with a suitable monitoring system was one of the crucial items before the beginning of Run 2 to ensure early detection of issues and to give a good overview of the whole pool. Our new monitoring page (cms-gwmsmon.cern.ch) utilizes the condor classAd mechanism to provide a complete picture of the whole submission infrastructure in CMS. Monitoring page includes useful information from HTCondor schedulers, central manager, glideinWMS frontend and factory. It also incorporates information about users and tasks making it easy for operators to provide support and debug issues.
        Speaker: Justas Balcas (California Institute of Technology (US))
      • 5:00 PM
        Networking in HTCondor 30m
        Learn how HTCondor navigates the twists and turns of modern networks, filled with firewalls, private networks, and multiple protocols. Topics will include CCB (Condor Connection Broker), shared port, and IPv4/6.
        Speaker: Jaime Frey
      • 5:30 PM
        Ask The Experts, Part II 30m
        Speaker: Todd Tannenbaum
    • 9:00 AM 10:00 AM
      ARC CE presentations and tutorials

      Going through different ways of running ARC CE for ATLAS computing; experiences in moving from Cream CE to ARC CE; setting up (1) a basic ARC CE, (2) ARC CE for WLCG with HTCondor, (3) non-gridftp ARC CE; ARC roadmap.

    • 9:00 AM 12:00 PM
      HTCondor and HTCondor CE office hours
    • 10:00 AM 10:30 AM
      Coffee break 30m
    • 10:30 AM 12:00 PM
      ARC CE presentations and tutorials

      Going through different ways of running ARC CE for ATLAS computing; experiences in moving from Cream CE to ARC CE; setting up (1) a basic ARC CE, (2) ARC CE for WLCG with HTCondor, (3) non-gridftp ARC CE; ARC roadmap.

      • 10:30 AM
        Concepts of the ARC CE - part 2 30m
        Speaker: Jon Kerr Nilsen (University of Oslo (NO))
      • 11:00 AM
        Migration from a CREAM/Torque cluster to ARC/Condor at the Liverpool T2 1h
        This talk will cover the specific measures used at the Liverpool grid site to provide multicore job slots for ATLAS using an ARC CE in front of a CONDOR batch system.
        Speaker: Stephen Jones (Liverpool University)
    • 12:00 PM 1:00 PM
      Lunch 1h
    • 1:30 PM 3:30 PM
      ARC CE presentations and tutorials

      Going through different ways of running ARC CE for ATLAS computing; experiences in moving from Cream CE to ARC CE; setting up (1) a basic ARC CE, (2) ARC CE for WLCG with HTCondor, (3) non-gridftp ARC CE; ARC roadmap.

    • 1:30 PM 6:00 PM
      HTCondor and HTCondor CE office hours
    • 3:30 PM 4:00 PM
      Coffee break 30m
    • 4:00 PM 6:00 PM
      ARC CE presentations and tutorials

      Going through different ways of running ARC CE for ATLAS computing; experiences in moving from Cream CE to ARC CE; setting up (1) a basic ARC CE, (2) ARC CE for WLCG with HTCondor, (3) non-gridftp ARC CE; ARC roadmap.

      • 4:00 PM
        Tech preview: Setting up ARC with Python-based backend 1h
        Speaker: Martin Skou Andersen (University of Copenhagen (DK))
      • 5:00 PM
        End-of-day discussion 1h
    • 6:20 PM 7:00 PM
      Facilities tour: PIC Tier-1 center 40m
    • 7:00 PM 7:20 PM
      PIC visit instructions 20m
      https://goo.gl/maps/5zJUgw36c6G2
      Speaker: Jose Flix Molina (Centro de Investigaciones Energ. Medioambientales y Tecn. - (ES)
    • 9:00 AM 11:00 AM
      ARC CE office hours
    • 9:00 AM 11:00 AM
      HTCondor and HTCondor CE office hours
      • 9:00 AM
        Coffee break 20m
    • 11:00 AM 11:30 AM
      Coffee Break 30m
    • 11:30 AM 1:00 PM
      ARC CE office hours
    • 11:30 AM 1:00 PM
      HTCondor and HTCondor CE office hours